Performance Rating
NVIDIA A100 PCIe 80 GB outperforms Intel Arc Pro B60 by 186.37% in the overall GPU ARK performance rating
NVIDIA A100 PCIe 80 GB
Expert Comparison
Intel Arc Pro B60 более энергоэффективный и дешевый вариант с TDP 200 Вт против 300 Вт у NVIDIA A100. Однако NVIDIA A100 значительно превосходит по производительности, особенно в вычислениях FP32, с пропускной способностью 1.94 ТБ/с против 456 ГБ/с у Intel. A100 также подходит для сложных вычислений и машинного обучения благодаря большей памяти и шине.
Contents:
Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering AdditionalMemory
Memory Size
+233%
80
ГБ
Memory Type
Memory Bandwidth
1.94 TB/s
Memory Bus Width
ML Performance
FP16 (Half Precision)
+217%
77.97
TFLOPS
BF16 (Brain Float)
311.84
TFLOPS
TF32 (TensorFloat)
155.92
Compute Power
FP32 (Single Precision)
+59%
19.49
TFLOPS
FP64 (Double Precision)
+217%
9.746
TFLOPS
CUDA Cores
+170%
6,912
RT Cores
20
Architecture & Compatibility
GPU Architecture
SM (Streaming Multiprocessor)
108
PCIe Version
ML Software Support
CUDA Version
CUDA Toolkit (first supported)
CUDA Toolkit status
Clocks & Performance
Base Clock
+88%
2,000
Boost Clock
+70%
2,400
Memory Clock
+57%
2,375
Power Consumption
Recommended PSU
-21%
550 W
Power Connector
TDP/TGP
-33%
200 W
Rendering
Texture Units (TMU)
+170%
432
ROP
20
L2 Cache
+1,900%
80 MB
Additional
Slots
Release Date
Display Outputs
Rent on Intelion Cloud
Available for rent on Intelion Cloud
